gjreda

Some context: I've been a jack-of-all-trades data scientist / machine learning engineer for the past 15 years (officially titled as an MLE the last four years).

I share that only because I think it plays a role in how I'm typically accustomed to working.

1. I found LangChain to be overkill for this use-case. While it might allow some to move more quickly when building, I found it to be cumbersome. My suspicion is this is largely because of my background - I understand how to build much of what's "under the hood" in LangChain. Because of this, I think it felt overly abstracted and I found the docs difficult to navigate and sometimes incomplete.

2. I used Qdrant via their docker image and it was simple to setup and start using. I didn't try to push the limits with it, so I can't say anything about performance. Because Qdrant runs as an http service, I found that it didn't fit well into my workflow - I'm accustomed to being able to visually inspect my data inside the interpreter, debugging, trying out commands, interacting and experimenting with my results, etc. Again, my suspicion is this is my own bias in how I typically work. Qdrant otherwise seemed very nice.

3. LanceDB felt powerful yet lightweight, and fit well into my workflow. It was far more intuitive for me. It was as if sqlite, the python data ecosystem, and a vector database had a child and named it LanceDB. Under the hood, it's built on Apache Arrow and integrates nicely with pandas, allowing me to seamlessly go from LanceDB table on disk, to pandas dataframe, and into some analysis or investigation of my LanceDB query results. This line [1] is a great example of why I liked it. This feels nicer to me than the world of API params and HTTP requests.

I'm working on using it in a large project now.

> For restaurant inventory, we will rapidly expand our recent pilots of putting non-partnered restaurants on the platform. For reasons we’ve discussed many times, we believe non-partnered options are the wrong long-term answer for diners, restaurants and shareholders. It is expensive for everyone, a suboptimal diner experience and rife with operational challenges. With that said, it is extremely efficient and cheap to add non-partnered inventory to our platform and it can at least ensure that all of our current and potential new diners have the option to order from any of their favorite restaurants now, even if it’s not the best solution. By leveraging non-partnered options, we believe we can more than double the number of restaurants on our platform by the end of 2020.

> At the same time, because we know that partnered relationships are critical to the long-term success of this business, we will be investing aggressively in our independent restaurant sales organization to support converting as many of these non-partnered restaurants to partnered relationships as quickly as possible and to take advantage of other innovations in the restaurant space, like virtual restaurants.